rakeshvar/rnn_ctc
Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
Supports both offline batch training and online incremental learning modes for sequence labeling tasks. Built on Theano with configurable RNN architectures (including bidirectional LSTMs), multiple optimizers (SGD, Adagrad, RMSprop), and learning rate annealing strategies. Includes a synthetic data generator for handwritten character recognition that can produce variable-length sequences with customizable alphabets and noise levels.
221 stars. No commits in the last 6 months.
Stars
221
Forks
81
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 26, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rakeshvar/rnn_ctc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
githubharald/CTCWordBeamSearch
Connectionist Temporal Classification (CTC) decoder with dictionary and language model.
githubharald/CTCDecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon...
nl8590687/ASRT_SpeechRecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
athena-team/athena
an open-source implementation of sequence-to-sequence based speech processing engine
hirofumi0810/tensorflow_end2end_speech_recognition
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)